How to Use the Gong MCP in LangChain

Q: Can I trace Gong MCP Server tool execution inside LangChain using LangSmith?

Yes. Every call to tools like getinteractionstats or listcalls shows up in your LangSmith trace as a distinct tool run. You can inspect the exact input parameters, output payloads, and latency of each Gong API call.

Q: Can a LangChain agent call multiple Gong tools in a single run?

Yes, LangChain excels at this. Your agent can run searchcalls to find specific meetings, pull their details with getcall, and then extract the transcript using gettranscript in a single, automated reasoning loop.

Build multi-step LangChain pipelines that inspect Gong call transcripts and trace agent reasoning in LangSmith.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gong MCP to LangChain

Create your Vinkius account to connect Gong to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Gong with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace Gong call analysis inside LangChain

Your LangChain agent can chain `list_calls` with `get_transcript` to find specific objections raised by prospects during sales demos. LangSmith traces the exact latency and token cost of pulling these massive Gong conversation logs so you can optimize your agent's prompts. If the Gong transcript flags a competitor, the LangChain agent automatically triggers `get_account` to verify the account owner. You see the entire multi-step LangChain run in your dashboard without guessing which Gong tool failed.

Build ReAct loops for sales coaching

Stop writing static scripts to grade sales reps in LangChain. This MCP Server lets your LangChain agent run a ReAct loop that pulls Gong scorecards via `list_scorecards` and evaluates them against raw call recordings using `get_call_media`. The LangChain agent decides on the fly whether to dig deeper into Gong interaction metrics using `get_interaction_stats` or move to the next rep. It acts as a dynamic supervisor that adapts based on what it finds in the data.

Match tracker keywords to CRM accounts

Connect your Gong data directly to your enterprise database integrations via this MCP Server in your LangChain pipeline. The LangChain framework feeds the output of `list_trackers` into a chain that cross-references specific Gong keyword alerts with account details from `list_accounts`. Instead of manual exports, the LangChain agent runs this pipeline in the background and flags Gong accounts where reps missed critical product mentions. You get clean, structured outputs ready for your LangChain memory or CRM updates.

Setup guide

Set up Gong MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Gong tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "gong-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Gong transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Gong. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Gong now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Gong MCP in LangChain

LangChain processes the raw text block directly within your prompt context. You can use a document splitter inside your chain to break down long transcripts from `get_transcript` before passing them to your LLM to avoid context window limits.

Yes. Every call to tools like `get_interaction_stats` or `list_calls` shows up in your LangSmith trace as a distinct tool run. You can inspect the exact input parameters, output payloads, and latency of each Gong API call.

Vinkius manages the authentication layer securely. You only need to pass your Vinkius endpoint token to the `MultiServerMCPClient` configuration, and your LangChain agent gets immediate, secure access to tools like `list_users`.

Yes, LangChain excels at this. Your agent can run `search_calls` to find specific meetings, pull their details with `get_call`, and then extract the transcript using `get_transcript` in a single, automated reasoning loop.

Your Gong call transcripts, audio files, and user records never touch external databases. Vinkius runs the server in an isolated, zero-trust sandbox, passing the data directly to your LangChain pipeline without keeping copies.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript